Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos.
Dongliang HeXiang ZhaoJizhou HuangFu LiXiao LiuShilei WenPublished in: CoRR (2019)
Keyphrases
- natural language descriptions
- reinforcement learning
- natural language
- spatio temporal
- reinforcement learning algorithms
- temporal information
- model free
- markov decision processes
- learning algorithm
- function approximation
- state space
- multi agent
- optimal policy
- policy search
- learning process
- neural network
- robotic control
- action selection
- learning problems
- transfer learning
- multi view
- dynamic programming